• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.157-165
• /
• 2022

As the stock market is affected by various circumstances including economic and political variables, predicting the stock market is considered a still open problem. When combined with corporate financial statement data analysis, which is used as fundamental analysis, and technical analysis with a short data generation cycle, there is a problem that the time domain does not match. Our proposed method, LSTE the operating profit and market outlook of a petrochemical company and estimates the sales and operating profit of the company, it was possible to solve the above-mentioned problems and improve the accuracy of stock price prediction. Extensive experiments on real-world stock data show that our method outperforms the 8.58% relative improvements on average w.r.t. accuracy.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.788-789
• /
• 2023

기존 도어락의 핀 인증 방식은 사용자에 따라 불편함을 느끼기도 한다. 이에 대한 솔루션으로 안면인식 도어락을 제안하며 Jetson nano에 face recognition 딥러닝 모델을 적용한 도어락을 제작한다. 거주자의 이미지를 촬영한 뒤 얼굴의 특징점을 분석하여 저장한다. 사용자가 도어락의 카메라에 인식되었을 때 저장된 안면 정보를 바탕으로 사용자가 거주자의 특징점과 일치하는지 확인한다. 거주자임이 인지되었을 때 도어락은 unlock되어 열리게 된다. 안면 인식 도어락 사용 시 보안상 취약해질 수 있는 기존 도어락의 핀 인증 방식에 대해 보안을 강화할 수 있으며 카메라를 통해 촬영된 사용자의 사진 및 영상을 활용하여 여러 서비스를 적용할 수 있다.

• Journal of the Korean Society of Radiology
• /
• v.8 no.3
• /
• pp.123-136
• /
• 2014

In this paper, we study to classify molecular imaging and applications to predict future. Molecular imaging in vivo at the cellular level and the molecular level changes taking place to be imaged, that is molecular cell biology and imaging technology combined with the development of the new field. Molecular imaging is used fluorescence, bioluminescence, SPECT, PET, MRI, Ultrasound and other imaging technologies. That is applied to monitoring of gene therapy, cell tracking and monitoring of cell therapy, antibody imaging, drug development, molecular interaction picture, the near-infrared fluorescence imaging of cancer using fluorescence, bacteria using tumor-targeting imaging, therapeutic early assessment, prediction and therapy. The future of molecular imaging would be developed through fused interdisciplinary research and mutual cooperation, which molecular cell biology, genetics, chemistry, physics, computer science, biomedical engineering, nuclear medicine, radiology, clinical medicine, etc. The advent of molecular imaging will be possible to early diagnosis and personalized treatment of disease in the future.

• Applied Microscopy
• /
• v.41 no.3
• /
• pp.147-154
• /
• 2011

Backscattered electrons (BSE) are generated at the impact of the primary electron beam on the specimen. BSE imaging provides the compositional contrast to resolve chemical features of sectioned block-face. A focused ion beam (FIB) column can be combined with a field emission scanning electron microscope (FESEM) to ensure a dual (or cross)-beam system (FIB-FESEM). Due to the milling of the specimen material by 10 to 100 nm with the gallium ion beam, FIB-FESEM allows the serial block-face (SBF) imaging of plastic-embedded specimens with high z-axis resolution. After contrast inversion, BSE images are similar to transmitted electron images by transmission electron microscopy. As another means of SBF imaging, a specialized ultramirotome has been incorporated into the specimen chamber of FESEM ($3View^{(R)}$). Internal structures of plastic-embedded specimens can be serially revealed and analyzed by $3View^{(R)}$ with a large field of view to facilitate three-dimensional reconstruction. These two SBF approaches by FESEM can be employed to unravel spatial association of (sub)cellular entities for a comprehensive understanding of complex biological systems.

• Applied Chemistry for Engineering
• /
• v.23 no.3
• /
• pp.271-278
• /
• 2012

In this work, we have prepared the nanocomposite by the reaction of mica and zinc oxide, and investigated the application of nanocomposite to UV protecting creams. Mica treated with 3-aminopropyltrimethoxysilane (APTMS) reacted with 1,4-phenylenediisothiocyanate (PDC) to give -N=C=S functionalized surface, which was further reacted with zinc oxides coated with APTMS to give mica-zinc oxide nanocomposites. The composites were characterized by EA, EDS, TGA, SEM, zeta potential measurement, powder XRD, and DRS UV/Vis analyses. Finally, we measured transmittances of ultraviolet protection creams manufactured by using mica composite covered with zinc oxides in the range of 280~400 nm. The nanocomposites developed in this work might be applicable as inorganic hybrid materials for UV protecting creams.

• Journal of the Korean Electrochemical Society
• /
• v.7 no.2
• /
• pp.100-107
• /
• 2004

The nano or micro sized structures of conducting polymer had been prepared by synthesizing the desired polymer within the pores of template of nano or micro porous membrane filter. In this study, we had tried to fabricate conducting polymer microstructures on an electrode by using electrochemical deposition adopting template synthesis. Our attention was focused on two different things, attaching template on the electrode and fabricating microstructures only at limited areas of the electrode. A conducting polymer, PEDiTT (poly 3,4-ethylenedithi-athiophene) solution was blended with PVA(polyvinyl alcohol) solution and used as an conducting adhesive. After attaching template membrane, the electrode were immersed in 0.5M pyrrole in 0.1M KCI solution, and electrochemical polymerization was performed. The growth process of the microstructures studied by SEM. The electrochemical fabrication of conducting polymer was performed by using two-electrode system. A large working electrode and a micro scale disc electrode were used for the confined area synthesis. Polymerization potential was 4V in an electrolytic solution made of KCI in deionized water. The optimum polymerization conditions were, i.e. (4V/100sec) for $250{\mu}m$ electrode and (6V/30 sec) for $10{\mu}m$ electrode.

• Korean Chemical Engineering Research
• /
• v.61 no.3
• /
• pp.388-393
• /
• 2023

The analysis of engineering data using neural network based on supervised learning has been utilized in various engineering fields such as optimization of chemical engineering process, concentration prediction of particulate matter pollution, prediction of thermodynamic phase equilibria, and prediction of physical properties for transport phenomena system. The supervised learning requires training data, and the performance of the supervised learning is affected by the composition and the configurations of the given training data. Among the frequently observed engineering data, the data is given in log-scale such as length of DNA, concentration of analytes, etc. In this study, for widely distributed log-scaled training data of virtual 100×100 images, available loss functions were quantitatively evaluated in terms of (i) confusion matrix, (ii) maximum relative error and (iii) mean relative error. As a result, the loss functions of mean-absolute-percentage-error and mean-squared-logarithmic-error were the optimal functions for the log-scaled training data. Furthermore, we figured out that uniformly selected training data lead to the best prediction performance. The optimal loss functions and method for how to compose training data studied in this work would be applied to engineering problems such as evaluating DNA length, analyzing biomolecules, predicting concentration of colloidal suspension.

• Applied Microscopy
• /
• v.39 no.1
• /
• pp.65-72
• /
• 2009

Cryo-SEM which enables specimens to be observed in frozen form has been used to study liquid specimens in their native states. Cryo-methods, sample preparation for cryo-SEM, are quite complex and involve several discrete but vitally interconnected steps which are rapid cooling, fracturing, sectioning, etching and coating. It is important to select practical techniques and to optimize conditions of each steps considering analytic purpose and specimen characters, viz., sample dimension, water contents. In this study, etching methods and sample preparation before freezing had been studied for observation of cyanobacteria, Synechocystis sp. PCC 6803 using cryo-SEM and their cryo-SEM images were compared to Conventional SEM (CSEM) images treated by chemical fixation. We could observe the improved morphological images of the pili of the surface and membranes of Synechocystis sp. PCC 6803 and the three-dimensional architectures of their biofilm, which were difficult to observe using chemical fixation and CSEM. These results suggest that cryo-methods/cryo-SEM are useful techniques for morphological study of biological specimen.

• Applied Chemistry for Engineering
• /
• v.31 no.2
• /
• pp.220-225
• /
• 2020

Hair is made of proteins containing various amino acids. Ultraviolet (UV) radiation is believed to be responsible for the most damaging effects of sunlight, and also plays an important role in hair aging. The purpose of this study was to investigate the changes in morphological and chemical structures after ultraviolet B (UVB) irradiation of human hair. The UVB-irradiated hair showed characteristic morphological and structural changes, compared to those of the normal hair. The result from a scanning electron microscope (SEM) equipped with an energy dispersive X-ray diffractometer (EDX) showed that the scale of UV-irradiated hair appeared to be rough and the amount of oxygen element was higher than that of the normal hair. Fluorescence and three dimensional (3D) topographical images were obtained by a confocal laser scanning microscope (CLSM). In 3D images, the green emission intensity of normal hair was much higher than that of fluorescing UVB-irradiated hair. The intensity of green emission reflects the intrinsic fluorescence of hair protein. Also, a fluorescent imaging method using fluorescamine reagent was used to identify the free amino groups resulting from a peptide bond breakage in UVB-irradiated hair. Strong blue fluorescence of UVB-irradiated hair, which indicates a very high level of amino groups, was observed by CLSM. Therefore, the fluorescamine as an extrinsic fluorescence could provide a useful tool to identify the peptide bond breakage in UVB-irradiated hair. Infrared image mapping was also employed to assess the cross-sections of normal and UVB-irradiated specimens to examine the oxidation of disulfide bonds. The degree of peak areas with strong absorbance for the disulfide mono-oxide was spread from the outside to the inside of hair. The spectroscopic techniques used alone, or in combination, launch new possibilities in the field of hair cosmetics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.41-46
• /
• 2023

Human urine is a process of excreting waste products in the blood, and it is easy to collect and contains various substances. Urinalysis is used to check for diseases, health conditions, and urinary tract infections. There are three methods of urinalysis: physical property test, chemical test, and microscopic test, and chemical test results can be easily confirmed using urine test strips. A variety of items can be tested on the urine test strip, through which various diseases can be identified. Recently, with the spread of smart phones, research on reading urine test strips using smart phones is being conducted. There is a method of detecting and reading the color change of a urine test strip using a smartphone. This method uses the RGB values and the color difference formula to discriminate. However, there is a problem in that accuracy is lowered due to various environmental factors. This paper applies a deep learning model to solve this problem. In particular, color discrimination of a urine test strip is improved in a smartphone using a lightweight CNN (Convolutional Neural Networks) model. CNN is a useful model for image recognition and pattern finding, and a lightweight version is also available. Through this, it is possible to operate a deep learning model on a smartphone and extract accurate urine test results. Urine test strips were taken in various environments to prepare deep learning model training images, and a urine test service application was designed using MobileNet V3.